Diverging Flows: Native Extrapolation Detection for Flow Matching Models
Flow Matching models are vulnerable to producing plausible but invalid outputs when given off-manifold inputs, leading to silent failures. The proposed Diverging Flows method enables a single model to perform both conditional generation and native extrapolation detection by enforcing inefficient transport for off-manifold inputs. Experiments on synthetic and real-world tasks show that this approach detects extrapolations effectively without sacrificing predictive accuracy or inference speed.
Why it matters: This work addresses a key safety concern for deploying flow-based generative models in high-stakes domains by providing a practical method for detecting extrapolation failures.
Full story at: arXiv Statistical ML ↗